Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "one"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickr
    -0.86
    lished
    -0.82
    rador
    -0.79
    achusetts
    -0.78
    hips
    -0.77
    rawler
    -0.74
    ipeg
    -0.74
    lishes
    -0.73
    ablishment
    -0.72
    anooga
    -0.71
    POSITIVE LOGITS
    gger
    1.08
    lihood
    0.92
    lla
    0.88
    xus
    0.87
    xual
    0.87
    cone
    0.86
    llo
    0.86
    lli
    0.85
    phrine
    0.84
    utral
    0.83
    Act Density 0.039%

    No Known Activations